Discovery of novel Li SSE and anode coatings using interpretable machine learning and high-throughput multi-property screening.

All-solid-state batteries with Li metal anode can address the safety issues surrounding traditional Li-ion batteries as well as the demand for higher energy densities. However, the development of solid electrolytes and protective anode coatings possessing high ionic conductivity and good stability with Li metal has proven to be a challenge. Here, we present our informatics approach to explore the Li compound space for promising electrolytes and anode coatings using high-throughput multi-property screening and interpretable machine learning. To do this, we generate a database of battery-related materials properties by computing [Formula: see text] migration barriers and stability windows for over 15,000 Li-containing compounds from Materials Project. We screen through the database for candidates with good thermodynamic and electrochemical stabilities, and low [Formula: see text] migration barriers, identifying promising new candidates such as [Formula: see text]N, [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], among others. We train machine learning models, using ensemble methods, to predict migration barriers and oxidation and reduction potentials of these compounds by engineering input features that ensure accuracy and interpretability. Using only a small number of features, our gradient boosting regression models achieve [Formula: see text] values of 0.95 and 0.92 on the oxidation and reduction potential prediction tasks, respectively, and 0.86 on the migration barrier prediction task. Finally, we use Shapley additive explanations and permutation feature importance analyses to interpret our machine learning predictions and identify materials properties with the largest impact on predictions in our models. We show that our approach has the potential to enable rapid discovery and design of novel solid electrolytes and anode coatings.

Surface energies of elemental crystals.

The surface energy is a fundamental property of the different facets of a crystal that is crucial to the understanding of various phenomena like surface segregation, roughening, catalytic activity, and the crystal's equilibrium shape. Such surface phenomena are especially important at the nanoscale, where the large surface area to volume ratios lead to properties that are significantly different from the bulk. In this work, we present the largest database of calculated surface energies for elemental crystals to date. This database contains the surface energies of more than 100 polymorphs of about 70 elements, up to a maximum Miller index of two and three for non-cubic and cubic crystals, respectively. Well-known reconstruction schemes are also accounted for. The database is systematically improvable and has been rigorously validated against previous experimental and computational data where available. We will describe the methodology used in constructing the database, and how it can be accessed for further studies and design of materials.

Thermal Stability and Reactivity of Cathode Materials for Li-Ion Batteries.

The thermal stability of electrochemically delithiated Li0.1Ni0.8Co0.15Al0.05O2 (NCA), FePO4 (FP), Mn0.8Fe0.2PO4 (MFP), hydrothermally synthesized VOPO4, LiVOPO4, and electrochemically lithiated Li2VOPO4 is investigated by differential scanning calorimetry (DSC) and thermogravimetric analysis, coupled with mass spectrometry (TGA-MS). The thermal stability of the delithiated materials is found to be in the order of NCA < VOPO4 < MFP < FP. Unlike the layered oxides and MFP, VOPO4 does not evolve O2 on heating. Thus, VOPO4 is less likely to cause a thermal run-away phenomenon in batteries at elevated temperature and so is inherently safer. The lithiated materials LiVOPO4, Li2VOPO4, and LiNi0.8Co0.15Al0.05O2 are found to be stable in the presence of electrolyte, but sealed-capsule high-pressure experiments show a phase transformation of VOPO4 → HVOPO4 → H2VOPO4 when VOPO4 reacts with electrolyte (1 M LiPF6 in EC/DMC = 1:1) between 200 and 300 °C. Using first-principles calculations, we confirm that the charged VOPO4 cathode is indeed predicted to be marginally less stable than FP but significantly more stable than NCA in the absence of electrolyte. An analysis of the reaction equilibria between VOPO4 and EC using a multicomponent phase diagram approach yields products and reaction enthalpies that are highly consistent with the experiment results.